ZWQbpkzl [none/use name]

chatgpt copilot^®

This is a grocery list manager. What the hell did it even get flagged for?

I say probably yes, but regardless I wouldn’t trust such a young project with only one contributor with my ssh connection.

Its like every commit is pushed directly to main triggering a new version. I wouldn’t trust that release cycle ever. Its just over a week old and is already on v3.

You’ll have to be more specific with how anthropic is debuging Firefox. There’s many sort of possible setups. In general though, you’ll need

• an llm model file
• some openai compatible server, eg lmstudio, llama.cpp, ollama.
• some sort of client to that server there’s a myriad of options here. OpenCode is the most like Claude. But there’s also more modular programmatic clients, which might suit a long term task
• the Firefox source code and/or an MCP server via some plugin.

You’ll also need to know which models your hardware can run. “Smarter” models require more ram. Models can run on both CPUs and GPUs but they run way faster on the GPU, if they fit in the VRAM.

Its quite explicitly malicious. If you do anything they think is not in national security interests: treason.